Application of quantum-behaved characteristic particle swarm optimisation algorithm in multi-objective optimisation of urban rail train
by Lili Yue; Mingjian Su; Baodi Xiao
International Journal of Computational Intelligence Studies (IJCISTUDIES), Vol. 11, No. 3/4, 2022

Abstract: This paper combines operation control strategy and operation curve to address the problems of frequent switching and high energy consumption of traditional ATO control policies. Firstly, based on the Pareto principle, the objective optimisation model is established based on urban rail trains' punctuality and energy consumption. Then, a multi-objective quantum particle swarm optimisation (MOQPSO) algorithm with fewer control parameters is adopted. The Gaussian mutation operator and crowding distance sorting method are introduced to select the global optimal guidance particles better, and the optimisation effect of the conventional MOPSO algorithm is compared. Finally, the actual data of the Beijing Subway Yizhuang Line are used to verify the algorithm. Simulation results show that the MOQPSO algorithm has advantages in convergence, diversity, and optimisation. At the same time, different control strategies are compared, and the results show that the improved hybrid control strategy has a better optimisation effect on the longer line.

Online publication date: Tue, 14-Feb-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Intelligence Studies (IJCISTUDIES):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com